查詢結果分析
來源資料
相關文獻
- Design of Probabilistic Neural Networks for Discrete Variables
- Neural-net Decoders for Linear Block Codes
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
- 運用類神經網路於股價指數之套利--以日經225指數為例
頁籤選單縮合
題名 | Design of Probabilistic Neural Networks for Discrete Variables=估算離散變數概率的類神經網路之設計 |
---|---|
作者姓名(中文) | 曾敏烈; | 書刊名 | 華岡工程學報 |
卷期 | 10 1996.03[民85.03] |
頁次 | 頁47-69 |
分類號 | 440.11 |
關鍵詞 | 概率分佈; 類神經網路; 漢明網路; Probability distributions; Neural networks; Hamming nets; |
語文 | 英文(English) |
中文摘要 | 神經網路很重要的一個特性是能由數據和經驗中學習。但是,數據很可能並不完整或不準確,情況也往往很不確定,而且多少也和經驗有點不同;如果只依據數據和經驗來做決定,很可能並不適用於新的場合。所以,應用概率來推論,有時有其必要性。因此,我們設計出一種所謂概率式漢明網路(probabilistic hamming net),可以有效地學得概率分佈,並且還提供了明確的比對(explicit matching)和多工(multiplexing)的機構。對於提高判斷的準確性,應有很大的助益。 |
英文摘要 | One of the main reasons for the popularity of neural networks lies in the ability to learn from data and/or experiences, which may compensate for what most expert systems might lack. However, since data may be incomplete and/or inaccurate and situations are usually uncertain and to some extent different from experiences, crisp decisions based on data or experiences are apt to fail in new situations. Therefore, the application of probabilistic inference seems indispensable in some circumstances. A probabilistic Hamming net is designed for discrete variables to effectively compute the probabilities and to provide explicit matching and multiplexing mechanisms. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。